Autonomous AI agents that perform tasks independently
syndicalt
SDK for Pathlight — visual debugging and observability for AI agents
copilotkit
AG-UI integration for Anthropic Claude Agent SDK
GitHub Actions
ACP agent in TypeScript that uses the Zhipu AI GLM series (specifically GLM-5.1 and GLM-4.7) as the reasoning core
mertdlkr
From one prompt to a finished product — fully autonomous. NexGSD turns any AI coding tool into a complete project engine: auto-plans, remembers across sessions, builds end-to-end, audits security & performance, deploys to production. 18 agents + 39 workfl
...morephl28
Convex component for agent memory backed by Convex vector search and Neo4j graph traversal.
barrymister
Sidecar agent for code-server-ops. REST endpoints over process and extension state, with Preview→Confirm mutations and optional bundled UI.
...morejkait
Shared runtime contracts for planner, todo, and session state across openclaw runtimes
namitjain07
Production-grade memory engine for AI agents
LangChain Python tool wrapping SBO3L — gate every agent payment intent through SBO3L's policy boundary.
ast-outline contributors
AST-based structural outline for source files (C#, Python, TypeScript/JavaScript, Java, Kotlin, Scala, Go, Rust, Markdown, YAML) — tree-sitter-powered, LLM-agent-first. Complement to ast-grep: ast-grep searches, ast-outline overviews.
...moreCrewAI tool wrapping SBO3L — gate every Crew action through SBO3L's policy boundary.
foo-ogawa
Contract-first specification and toolchain for command line interfaces
Settle Protocol contributors
Settle protocol SDK for Python — receipt kernel, verifyReceipt, and LangChain + CrewAI adapters.
LLM-native database kernel — persistent KV cache memory for autonomous AI agents
Jeel Thummar
Episodic evaluation framework for LLM agents — works with any framework
CLI tool to maintain hybrid LLM Wikis for multi-language projects.
AI market research simulation using NVIDIA Nemotron personas and Claude Code Agents
garudust-org
🦅 Self-improving Rust AI agent — multi-agent delegation, auto-skill learning, multi-platform chat bots, persistent memory, MCP tools, cron scheduling and a production-grade gateway
...moreArch1eSUN
Local-first sovereign AI agent runtime — lives on your own machines. Persistent identity, long-term memory, full-sensory perception, sandboxed tool use, deterministic event log: every step is replay-able, fork-able, audit-able. Internal north star: Hermes. macOS / iOS / CLI. AGPL-3.0 + commercial.
...morehawkli-1994
本书围绕 DeerFlow 2.0，从理论到源码，系统讲解如何进行二次开发。
walkinglabs
An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
...morecARnage501
Agentic Reality Compiler is a governed system for compiling model-world contact into admissible agent reality. Governed Contact Runtime v1 is the first runnable implementation of the Agentic Reality Compiler: a deterministic runtime boundary for model-world contact.
...moreHugo Farajallah
Elegant Python API for Claude CLI agents
CLI tool for autonomous task execution via Claude Code